INDEX

Explanations

terms related to "ret" or "retinal" processes, particularly in a biological context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gonic

-0.62

newInstance

-0.62

logrus

-0.59

ContentAsync

-0.59

Dougall

-0.56

ึ้น

-0.55

épisode

-0.54

 Mannes

-0.54

Życiorys

-0.53

 blocco

-0.53

POSITIVE LOGITS

Ret

0.89

RET

0.82

Ret

0.75

ret

0.75

 retr

0.67

ret

0.61

 retribu

0.60

)]:

0.60

 retriever

0.57

 Retriever

0.56

Activations Density 0.079%

terms related to "ret" or "retinal" processes, particularly in a biological context

No Comments

No Known Activations